Multi-Spatial Pyramid Feature and Optimizing Focal Loss Function for Object Detection

计算机科学 目标检测 人工智能 棱锥(几何) 功能(生物学) 模式识别(心理学) 特征(语言学) 对象(语法) 计算机视觉 数学 生物 几何学 语言学 进化生物学 哲学
作者
Shengye Wang,Zhong Qu,Le-yuan Gao
出处
期刊:IEEE transactions on intelligent vehicles [Institute of Electrical and Electronics Engineers]
卷期号:9 (1): 1054-1065 被引量:10
标识
DOI:10.1109/tiv.2023.3282996
摘要

Previous deep convolutional neural network research has made significant progress toward improving the speed and accuracy of object detection. However, despite these advancements, the inaccurate detection of multi-object (small objects) remains challenging in the traffic environments. In this article, we propose a new architecture called YOLOM, which is specifically designed to achieve enhanced multi-object (small objects) detection precision. YOLOM incorporates several innovative features: a multi-spatial pyramid (MSP), an optimized focal loss (OFLoss) function, and an objectness loss that incorporates effective intersection over union (EIoU) calculations. These features collectively yield enhanced accuracy and reduce the miss rate of small objects, particularly in the multi-object cases. According to the sizes of receptive field features with different spatial scales with pooling layers, we propose the MSP module. We optimize the focal loss as a classification function instead of the cross-entropy loss, which solves some class imbalance problems caused by anchor-free detection when encountering disparate datasets. Due to the superior performance of EIoU in confidence scoring, we use EIoU to participate in the objectness loss calculation of our work. Therefore, our method substitutes EIoU for YOLOX's objectness loss. The experimental results demonstrate that our strategies significantly outperform some end-to-end object detection methods.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
苏y完成签到,获得积分10
2秒前
华仔应助嘻哈采纳,获得10
2秒前
科研通AI5应助优秀的绿蕊采纳,获得10
5秒前
健忘的初翠完成签到,获得积分10
5秒前
7秒前
lwm不想看文献完成签到 ,获得积分10
7秒前
9秒前
拼搏一曲发布了新的文献求助10
10秒前
CAOHOU应助科研通管家采纳,获得10
11秒前
共享精神应助科研通管家采纳,获得10
11秒前
CAOHOU应助科研通管家采纳,获得10
11秒前
SYLH应助科研通管家采纳,获得20
11秒前
乐乐应助科研通管家采纳,获得10
11秒前
汉堡包应助科研通管家采纳,获得10
11秒前
FashionBoy应助科研通管家采纳,获得10
11秒前
桐桐应助科研通管家采纳,获得10
11秒前
11秒前
深情安青应助科研通管家采纳,获得10
11秒前
CAOHOU应助科研通管家采纳,获得10
11秒前
SYLH应助科研通管家采纳,获得10
11秒前
CAOHOU应助科研通管家采纳,获得10
11秒前
Owen应助科研通管家采纳,获得10
12秒前
SYLH应助科研通管家采纳,获得10
12秒前
SYLH应助科研通管家采纳,获得10
12秒前
12秒前
酷波er应助科研通管家采纳,获得10
12秒前
wushuwen发布了新的文献求助10
12秒前
13秒前
xuan完成签到,获得积分10
14秒前
完美世界应助段一帆采纳,获得10
16秒前
少敏敏完成签到,获得积分10
18秒前
may发布了新的文献求助10
18秒前
23秒前
25秒前
兜兜关注了科研通微信公众号
25秒前
wbh完成签到,获得积分10
26秒前
太牛的GGB发布了新的文献求助10
26秒前
wbh发布了新的文献求助10
28秒前
乐乐应助may采纳,获得10
28秒前
顺利的梦菲完成签到 ,获得积分10
29秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989378
求助须知:如何正确求助?哪些是违规求助? 3531442
关于积分的说明 11254002
捐赠科研通 3270126
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809173